摘要
钢轨表面缺陷检测是保障铁路安全运行的重要一环,通过分析钢轨表面缺陷检测的必要性和现有检测方法的不足,提出了一种基于注意力机制与混合监督学习的钢轨表面缺陷检测模型。针对现有模型参数量大、部署成本高的问题,提出了端到端的钢轨缺陷检测模型,利用注意力模块引导特征丛的生成,提高缺陷检测速度,降低模型部署成本;针对实际应用中存在的异常样本少、标注成本高等问题,研究粗糙标签与混合监督对模型的影响,对像素级标签进行数据处理,使标签的不同区域获得不同的关注,降低模型对标签的依赖性。最终在实际钢轨数据集上进行实验验证,结果表明在图像级标签样本中加入少量像素级标签样本的混合监督学习可获得与全监督学习相当的性能,模型的分类准确率达99.7%。
Rail surface defect detection is an important part of ensuring railway safety.By analyzing the necessity of rail surface defect detection and the shortcomings of existing detection methods,a rail surface defect detection model based on attention module and hybrid-supervised learning is proposed.Aiming at the problem of a large number of parameters and high deployment cost of existing model,an end-to-end rail defect detection model is proposed.The attention module is used to guide the generation of feature clusters,which improves the speed of defect detection and reduces the cost of model deployment.In view of the problems of few abnormal samples and the high cost of labeling in practical applications,the influence of rough labeling and hybrid supervision is studied,and the pixel-level label data is processed to make different areas of the label get different attention and reduce the dependence of model on label.Finally,experiments are carried out on the actual rail datasets.and the results show that the performance of hybrid-supervised learning is equivalent to that of full supervised learning by adding a small amount of pixel-level label samples to image-level label samples,and the classification accuracy of the model reaches 99.7%.
作者
赵晨阳
张辉
廖德
李晨
ZHAO Chen-yang;ZHANG Hui;LIAO De;LI Chen(School of Electrical&Information Engineering,Changsha University of Science and Technology,Changsha 410114,China;School of Robotics,Hunan University,Changsha 410012,China)
出处
《计算机科学》
CSCD
北大核心
2022年第S02期488-493,共6页
Computer Science
基金
国家重点研发计划(2018YFB1308200)
国家自然科学基金(61971071,6202780012)
湖南省杰出青年科学基金(2021JJ10025)
长沙市科技重大专项(kh2003026)
机器人学国家重点实验室联合开放基金(2021-KF-22-17)
中国高校产学研创新基金(2020HYA06006)
关键词
表面缺陷检测
深度学习
注意力
小样本
粗糙标签
Surface defect detection
Deep learning
Attention
Small-sized datasets
Rough label
作者简介
赵晨阳,zhaochenyang920@163.com,born in 1997,postgraduate.Her main research interests include covers image processing and deep learnin;通信作者:张辉,zhanghuihby@126.com,born in 1983,Ph.D,professor,IEEE member.His main research interests include machine vision,sparse representation and vision tracking.
